Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    weight loss

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Sele
    -0.06
     مک
    -0.06
    yped
    -0.06
     نمی
    -0.06
    =post
    -0.06
     SOME
    -0.06
    !_
    -0.06
    (cp
    -0.06
     detay
    -0.06
     sendMessage
    -0.06
    POSITIVE LOGITS
     funnel
    0.06
     emulate
    0.06
    .Flow
    0.06
    افع
    0.06
    xl
    0.06
    ßer
    0.06
     Boca
    0.06
    <byte
    0.06
    nothrow
    0.06
    teri
    0.06
    Act Density 0.019%

    No Known Activations